The Journal of China Universities of Posts and Telecommunications ›› 2019, Vol. 26 ›› Issue (2): 17-29.doi: 10.19682/j.cnki.1005-8885.2019.1003

• Artificial intelligence • Previous Articles     Next Articles

Multiple feature fusion for unimodal emotion recognition

Yang Lingzhi, Ban Xiaojuan, Michele Mukeshimana, Chen Zhe   

  1. 1. School of Computer and Communication Engineering, Beijing Key Laboratory of Knowledge Engineering for Materials Science, University of Science and Technology Beijing, Beijing 10083, China
    2. Citic Pacific Special Steel Holdings Qingdao Special Iron and Steel Company Limited
    3. Faculity of Engineering Sciences, University of Burundi, Bujumbura P. O. Box 1550 Bujumbura, Burundi
    4. Qingdao Hisense Group Company Limited, Qingdao 266000, China
  • Received:2018-08-07 Revised:2019-04-04 Online:2019-04-30 Published:2019-06-14
  • Contact: Corresponding author: Yang Lingzhi, E-mail:
  • About author:Corresponding author: Yang Lingzhi, E-mail:
  • Supported by:
    This work was supported by the National Key Research and Development Program of China (2016YFB1001404), and the National Natural Science Foundation of China (61873299, 61702036, 61572075).

Abstract: A new semi-serial fusion method of multiple feature based on learning using privileged information (LUPI) model was put forward. The exploitation of LUPI paradigm permits the improvement of the learning accuracy and its stability, by additional information and computations using optimization methods. The execution time is also reduced, by sparsity and dimension of testing feature. The essence of improvements obtained using multiple features types for the emotion recognition (speech expression recognition), is particularly applicable when there is only one modality but still need to improve the recognition. The results show that the LUPI in unimodal case is effective when the size of the feature is considerable. In comparison to other methods using one type of features or combining them in a concatenated way, this new method outperforms others in recognition accuracy, execution reduction, and stability.

Key words: multiple feature, LUPI, emotion recognition, semi-serial fusion method

CLC Number: